Control Systems and Computers, N6, 2017, Article 5


Upr. sist. maš., 2017, Issue 6 (272), pp. 41-51.

UDC 574:004.2

Andrej O. Fefelov – PhD in Techn.Sciences, Associated Professor, the Design Department,,

Volodymyr I. Lytvynenko – Doctor of Technical Sciences, Professor, Head of the Department of Informatics and Computer Science,,

Muchamed Ali Taif –  Graduate student of the Department of Informatics and Computer Science,

Mariia O. Voronenko –  PhD in Techn. Sciences, Associate Professor, the Department of Informatics and Computer Science,

Kherson National Technical University, Beryslavske high-way, 24, Kherson, 73008, Ukraine

Reconstruction of the S-System by the Hybrid Algorithm of the Clonal Selection and Differential Evolution

Introduction. Reconstruction or reverse engineering is a process of a conclusion of the structural and dynamic characteristics of the system under study on the basis of the observations of its behavior and its specific knowledge in the subject domain. Now days, many different models and methods of  gene regulatory reconstruction have been developed, which have both advantages and disadvantages. At the choice of descriptive model it is necessary to consider the fact that the mathematical models, as a rule, have their own structure and a number of parameters which need to be identified. Different algorithms have been used so far to address the problem of finding the gene regulatory network. Most of them are evolutionary approaches or swarm based approaches. Genetic algorithms, genetic programming, memetic algorithm, clonal algorithm, membrane algorithms, evolution strategy, differential evolution, self adaptive differential evolution, particle swarm optimization are some of the widely used techniques. These algorithms are population-based search algorithms. Most of them starts with the random solutions and try to improve it using the multiple iterations.

Purpose. The aim of this work is to develop an effective hybrid method for the reconstruction of the gene regulatory networks, which will increase the rate of convergence in solving the problem of the S-system optimizing.

Method. We propose a hybrid method for reconstructing the GRN. This method is based on the hybridization technology, which allows combining the best qualities of the algorithm of clonal selection and the algorithm of differential evolution.

Results. We propose a hybrid method of reconstruction GRN, allowing to increase the convergence rate and accuracy of the optimization algorithm to solve the problem of identification S-system. The S-system was applied, as a computational model. Parameters and structure were calculated by using the clonal selection algorithm and algorithm differential evolution. The gene expression profiles are used as input data. They were  represented by time series of changes in the expression products concentration. The experiments have shown the negative effect of the differential evolution operators application such as selection and crossover. On the other hand, a significant positive effect of mutation operator is shown, which is used in the algorithm of the differential evolution.

Conclusion. The comparative experiments results confirmed the advantages developed a hybrid method and an algorithm similar to the computational methods. The developed method and  algorithm allowed to increase the speed of algorithms optimization convergence and simultaneously to increase their accuracy in solving the problem of the S-system reconstruction. It can be used to modify evolutionary algorithms or artificial immune systems.

Keywords: gene regulatory networks, reverse engineering, gene expression, ordinary differential equations, S-system, clonal selection algorithm, differential evolution, structural-parametric identification, convergence of the algorithm.

 Download full text!

  1. CSETE, M., DOYLE, J., 2002. “Reverse Engineering of Biological Complexity”, Science, 295, pp. 1664–1669.
  2. Cho, K.H., Choo S.M., Jung S.H. et al., 2007. “Reverse engineering of gene regulatory networks”. IET System Biology, 1, pp. 149–163.
  3. DERISI, J.L., LYER, V.R., BROWN, P.O., 1997. “Exploring the metabolic and genetic control of gene expression on a genomic scale”, Science, 278, pp. 680–686.
  4. LIANG, S., FUHRMAN, S., SOMOGYI, R., 1998. “Reveal, a general reverse engineering algorithm for inference of genetic network architectures”, Pacific Symposium on Biocomputing (PSB ’98), Jan. 1998: Proceedings, Maui, Hawaii, USA, pp. 18–29.
  5. D’HAESELEER, P., WEN, X., FUHRMAN S. et al., 1999. “Linear modeling of mRNA expression levels during CNS development and injury”. 4th Pacific Symposium on Biocomputing (PSB ’99), Jan. 1999: Proceedings, Maui, Hawaii, USA., pp. 41–52.
  6. CHEN, T., HE, H.L., CHURCH, G.M., 1999. “Modeling gene expression with differential equations”, Pacific Symposium Biocomputing. Maui, Hawaii, USA, pp. 29–40.
  7. SCHAFER, J., STRIMMER, K., 2005. “An empirical Bayes approach to inferring large-scale gene association networks”, Bioinformatics, 21(6), pp. 754–764.
  8. FRIEDMAN, N., LINIAL, M., NACHMAN, I. et al., 2000. “Using Bayesian networks to analyze expression data”, J. of Computational Biology, 7(3–4), pp. 601–620.
  9. HACHE, H., WIERLING, C., LEHRACH, H. ET AL., 2007. “Reconstruction and validation of gene regulatory networks with neural networks”. 2nd Foundations of Systems Biology in Engineering Conference (FOSBE ’07), Sept. 2007: proceedings, Stuttgart, Germany, pp. 319–324.
  10. FEFELOV, A.A, LYTVYNENKO, V.I, TAIF, M.A., LURIE, I.A., 2017. “Hybrid Approach for Gene Regulatory Networks Reconstruction by a System of Ordinary Differential Equations”. Upr. sist. maš., 3, pp. 63–72. (In Russian).
  11. Rangel, C., Angus, J., Ghahramani Z. et al., 2004. “Modeling T-cell activation using gene expression profiling and state-space models”. Bioinformatics, 20(9), pp. 1361–1372.
  12. SAVAGEAU, M.A., 1988. “Introduction to S-systems and the underlying power-law formalism”, Mathematical and Computer Modelling, 11, pp. 546–551.
  13. DASGUPTA, D., 1999. Artificial Immune Systems and Their Applications, Springer-Verlag, 306 p.
  14. DE CASTRO, L.N., TIMMIS, J., 2002. “Artificial Immune Systems: A New Computational Intelligence Approach”, Heidelberg, Springer, 357 p.
  15. BURNET, F.M., 1976. “A modification of jerne’s theory of antibody production using the concept of clonal selection”, CA: a cancer journal for clinicians, 26(2), pp. 119–121.
  16. De CASTRO, L.N., Von ZUBEN, F.J., 2002. “Learning and optimization using the clonal selection principle”, IEEE Transactions on Evolutionary Computation, 6(3), pp. 239–251.
  17. FEFELOV, A.A., LITVINENKO, V.I., TAIF, M.A. et al., 2017. Parametric Identification of the S-System by the Modified Clonal Selection Algorithm, Upr. sist. maš., 5, pp. 43–53. (In Russian).
  18. STORN, R., PRICE, K.V., 2997. “Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces”, J. of Global Optimization, 11(4), pp. 341–359.
  19. STORN R., PRICE K.V., 1996. “Minimizing the real function of the ICEC’96 contest by differential evolution”, IEEE Int. Conf. on Evolutionary Computation, May 1996: proceedings, Nagoya, Japan, pp. 842–844.
  20. TOMINAGA, D., KOGA, N., OKAMOTO, M., 2000. “Efficient numerical optimization algorithm based on genetic algorithm for inverse problem”, Genetic and Evolutionary Computation Conference (GECCO ’00), July 2000: proceedings, Las Vegas, Nevada, USA, 251, pp. 251–258.
  21. KIM, K.-Y., CHO, D.-Y., ZHANG, B.-T., 2006. “Multi-stage evolutionary algorithms for efficient identification of gene regulatory networks”, Applications of evolutionary computing: EvoWorkshops 2006, Apr. 2006: proceedings, Budapest, Hungary, pp. 45–56.
  22. FEFELOV, A.A., LITVINENKO, V.I., TAIF, M.A. et al., 2017. “Object-Oriented Architecture of the Information System for the Reconstruction of the Gene Regulatory Networks”, Upr. sist. maš., 4, pp. 67–75, 82. (In Russian).
  23. LAMPINEN, J., ZELINKA, J., 2000. “On stagnation of the differential evolution algorithm”, 6th Int. Conf. on Soft Computing MENDEL 2000, June 2000: proceedings, Brno, Czech Republic, pp. 76–83.

Recieved 04.10.2017